human evals on small teams for Gemma

[relaynest82]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.

[lablab]

What exact setup are you running? Is this local-only or are you routing anything externally?

[macroforge]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.